Modeling the world. Remodeling video.
TwelveLabs models can see and reason about video like no other AI – and they set the standard for a new era of video data interaction.
Marengo transforms text, audio, image, and video into numerical representations called embeddings.
Marengo
2.7
Where power meets potential.
Search
Introducing ‘any-to-any’ search
Marengo’s state-of-the-art ‘any-to-any’ search helps you pinpoint exact moments in vast video libraries, or allow customers to find any video moment within your platform.
Embed
Introducing ‘rich embeddings’
With Marengo, it’s easy to build complex features like semantic search, hybrid search, anomaly detection, and more.
Marengo’s latest breakthroughs.
Pegasus understands video and generates accurate descriptions and analysis.
Pegasus
1.2
Where words and moving image unite.
Generate
Generate understanding with Pegasus
With video-to-text generation, Pegasus redefines how humans interact with video data. Intuitive, versatile, and powerful – this is human-level reasoning, at AI scale.
Pegasus’ latest frontiers.
We’re fundamentally transforming how people see, experience and use video through AI.
A Joint Sequence Fusion Model for Video Question Answering and Retrieval
ECCV 2018
1st place in LSMDC challenge in ICCV 2017
AdaCoF: Adaptive Collaboration of Flows for Video Frame Interpolation
CVPR 2020
Character Grounding and Re-Identification in Story of Videos and Text Descriptions
ECCV 2020
1st place in LSMDC challenge in ICCV 2019
